Word2vec - Wikipedia
5
Public whispers
5
Contributors
2026-07-17 10:03:07
First whispered
Public whispers on this page
Text Highlight2026-07-17 13:24:07
Original Highlight Excerpt
"skip-gram and CBOW are exactly the same in architecture. They only differ in the objective function during training."
Whisper Note
So the magic is all in the loss function, neat.
Text Highlight2026-07-17 13:15:07
Original Highlight Excerpt
"skip-gram and CBOW are exactly the same in architecture. They only differ in the objective function during training."
Whisper Note
Huh, I always thought they had different layers too, good to know.
Text Highlight2026-07-17 10:21:07
Original Highlight Excerpt
"Word2vec is a technique in natural language processing for obtaining vector representations of words."
Whisper Note
Cool, but does it actually handle polysemy well or just average meanings?
Text Highlight2026-07-17 10:12:07
Original Highlight Excerpt
"Word2vec is a technique in natural language processing for obtaining vector representations of words."
Whisper Note
I remember when this came out, it was a game changer for NLP research.
Text Highlight2026-07-17 10:03:07
Original Highlight Excerpt
"Word2vec is a technique in natural language processing for obtaining vector representations of words."
Whisper Note
So word2vec is basically how computers learn word meanings from context, right?
Share this page's whispers
Short link
https://domwhisper.com/s/fa0d2734c92aEmbed snippet
<iframe src="https://domwhisper.com/embed/fa0d2734c92a" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on en.wikipedia.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension